中文
相关论文

相关论文: GUI-GENESIS: Automated Synthesis of Efficient Envi…

200 篇论文

Large language model (LLM) agents learn by interacting with environments, but long-horizon training remains fundamentally bottlenecked by sparse and delayed rewards. Existing methods typically address this challenge through post-hoc credit…

Graphical User Interface (GUI) Agents powered by Multimodal Large Language Models (MLLMs) show significant potential for automating tasks. However, they often struggle with long-horizon tasks, leading to frequent failures. Process Reward…

人工智能 · 计算机科学 2025-10-06 Tao Xiong , Xavier Hu , Yurun Chen , Yuhang Liu , Changqiao Wu , Pengzhi Gao , Wei Liu , Jian Luan , Shengyu Zhang

This survey reviews how large language models (LLMs) are transforming synthetic training data generation in both natural language and code domains. By producing artificial but task-relevant examples, these models can significantly augment…

计算与语言 · 计算机科学 2025-11-21 Mihai Nadas , Laura Diosan , Andreea Tomescu

Denoising in the sRGB image space is challenging due to large noise variability. Although end-to-end methods perform well, their effectiveness in real-world scenarios is limited by the scarcity of real noisy-clean image pairs, which are…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Jaekyun Ko , Dongjin Kim , Soomin Lee , Guanghui Wang , Tae Hyun Kim

Recent advances in GUI agents have achieved remarkable grounding and action-prediction performance, yet existing models struggle with unreliable reward signals and limited online trajectory generation. In this paper, we introduce Orcust, a…

人工智能 · 计算机科学 2025-09-23 Junyu Lu , Songxin Zhang , Zejian Xie , Zhuoyang Song , Jiaxing Zhang

Remarkable progress has been achieved in synthesizing photo-realistic images with generative adversarial networks (GANs). Recently, GANs are utilized as the training sample generator when obtaining or storing real training data is expensive…

机器学习 · 计算机科学 2022-12-22 Bo Zhao , Hakan Bilen

The goal of continuous control is to synthesize desired behaviors. In reinforcement learning (RL)-driven approaches, this is often accomplished through careful task reward engineering for efficient exploration and running an off-the-shelf…

LLM-based (Large Language Model) GUI (Graphical User Interface) agents can potentially reshape our daily lives significantly. However, current LLM-based GUI agents suffer from the scarcity of high-quality training data owing to the…

人工智能 · 计算机科学 2025-05-26 Danyang Zhang , Situo Zhang , Ziyue Yang , Zichen Zhu , Zihan Zhao , Ruisheng Cao , Lu Chen , Kai Yu

Image generation abilities of text-to-image diffusion models have significantly advanced, yielding highly photo-realistic images from descriptive text and increasing the viability of leveraging synthetic images to train computer vision…

计算机视觉与模式识别 · 计算机科学 2025-02-10 Jiahui Chen , Amy Zhang , Adriana Romero-Soriano

Many real-world problems are compositional - solving them requires completing interdependent sub-tasks, either in series or in parallel, that can be represented as a dependency graph. Deep reinforcement learning (RL) agents often struggle…

机器学习 · 计算机科学 2022-01-25 Izzeddin Gur , Natasha Jaques , Yingjie Miao , Jongwook Choi , Manoj Tiwari , Honglak Lee , Aleksandra Faust

In this paper, we focus on the task of conditional image generation, where an image is synthesized according to user instructions. The critical challenge underpinning this task is ensuring both the fidelity of the generated images and their…

计算机视觉与模式识别 · 计算机科学 2025-03-20 Guiyu Zhang , Huan-ang Gao , Zijian Jiang , Hao Zhao , Zhedong Zheng

We propose a machine learning framework to synthesize reactive controllers for systems whose interactions with their adversarial environment are modeled by infinite-duration, two-player games over (potentially) infinite graphs. Our…

计算机科学与博弈论 · 计算机科学 2020-11-03 Daniel Neider , Oliver Markgraf

Reward models (RMs) play a critical role in aligning language models through the process of reinforcement learning from human feedback. RMs are trained to predict a score reflecting human preference, which requires significant time and cost…

计算与语言 · 计算机科学 2024-10-21 Zihuiwen Ye , Fraser Greenlee-Scott , Max Bartolo , Phil Blunsom , Jon Ander Campos , Matthias Gallé

Autonomous agents for Graphical User Interfaces (GUIs) are revolutionizing human-computer interaction, yet their reliance on text-based instructions imposes limitations on accessibility and convenience, particularly in hands-free scenarios.…

计算与语言 · 计算机科学 2025-11-27 Wenkang Han , Zhixiong Zeng , Jing Huang , Shu Jiang , Liming Zheng , Longrong Yang , Haibo Qiu , Chang Yao , Jingyuan Chen , Lin Ma

We introduce Procgen Benchmark, a suite of 16 procedurally generated game-like environments designed to benchmark both sample efficiency and generalization in reinforcement learning. We believe that the community will benefit from increased…

机器学习 · 计算机科学 2020-07-28 Karl Cobbe , Christopher Hesse , Jacob Hilton , John Schulman

Post-Training Multimodal Large Language Models (MLLMs) to build interactive agents holds promise across domains such as computer-use, web navigation, and robotics. A key challenge in scaling such post-training is lack of high-quality…

A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains…

The use of synthetic data in machine learning applications and research offers many benefits, including performance improvements through data augmentation, privacy preservation of original samples, and reliable method assessment with fully…

机器学习 · 计算机科学 2026-04-13 Joanna Komorniczak

Recent advances in vision-language models have enabled mobile GUI agents to perceive visual interfaces and execute user instructions, but reliable prediction of action consequences remains critical for long-horizon and high-risk…

Autonomous agents that navigate Graphical User Interfaces (GUIs) to automate tasks like document editing and file management can greatly enhance computer workflows. While existing research focuses on online settings, desktop environments,…